Semester II Question bank

Paper: Soft Computing

Course Code: - PSDS202

Chapter 1 Artificial Neural Network

Q.1 Define an artificial neural network.

Q.2 Draw a simple artificial neuron and explain.
Q.3 List and explain the main components of biological neuron.
Q.4 Compare and contrast biological neuron and artificial neuron.
Q.5 Explain supervised and unsupervised learning.
Q.6 Differentiate between supervised and unsupervised learning.
Q.7 What is the necessity of activation function. List the commonly used
activation and explain.
Q.8 Define the terms
(a) Weight
(b) Bias
(c) Threshold
(d) Learning rate parameter
(e) Linear separability
(f) Excitatory weight
(g) Inhibitory weight
Q.9 Explain McCulloch Pitt/ Describe McCulloch Pitt/ Note on McCulloch Pitt.
Q.10 Explain Hebb’s network/ Describe Hebb’s network / Note on Hebb’s
network.
Q.11 Explain Perceptron/ Describe Perceptron/ Note on Perceptron.
Q.12 Explain Adaline/ Describe Adaline / Note on Adaline.
Q.13 Explain Back-propagative network/ Describe Back-propagative network /
Note on Back-propagative network.
Q.14 Explain Madaline / Describe Madaline/ Note on Madaline.
Q.15 Explain Radial bias function network/ Describe Radial bias function
network/ Note on Radial bias function network.
Q. 16 Explain Time delay neural network/ Describe Time delay neural network
/ Note on Time delay neural network.
Q.17 Solve single input McCulloch-Pitts (NOT gate)
For W1 =-1, b=0 Condition X1 =0, X2= 1
Q.18 Solve two-input McCulloch Pitts (OR gate)
For W1 =W2 = 1, b=-1
Conditions [a] X1=X2 = 0 [b] X1= 0 , X2= 1 [c] X1= 1, X2= 0 [d] X1 = X2= 1
Draw a hyperline for Class A and Class B of the Boolean function
Class A is b + W1X1 +W2X2 ≥ 0 Class B is b + W1X1 +W2X2 < 0
Q.19 Solve two-input McCulloch Pitts for AND gate
B = -2, w1 = w2 = 1.
Conditions [a] X1=X2 = 0 [b] X1= 0 , X2= 1 [c] X1= 1, X2= 0 [d] X1 = X2= 1
Q.20 In a public transport there is a seat for specially-abled and senior citizen.
There are four given situations. You need to decide when the seat can be
occupied.
[a] Mention the situations or scenarios.
[b] Analyse the situations using the McCulloch-Pitts neural model.
[c] Use the value of both weights as 1 and scenarios as 1 and 0, b= 1, threshold
as 1.
Q.21 Design a Hebb’s network to implement logical AND function (use bipolar
inputs and targets).
a. Predict the accuracy.
b. Construct the decision boundary
c. Draw the network.
Q.22 Using HEBB network solve the OR gate problem if the learning rate is
0.5.
a. Predict the accuracy.
b. Construct the decision boundary
c. Draw the network.
Q.23 Using HEBB rule, find the weights required to perform the classification
pattern of the inputs given. The input patter “+” has value 1 and the empty
squares have value -1. Draw the network architecture.
Pattern 1 output value is 1, Pattern 2 output value is 0

+ + + + + +
+ + +
+ + + + + +

Pattern 1 Pattern 2

Q.24 Using HEBB rule, classify the two-dimensional input pattern. Draw the
network architecture. Pattern 1 output value is 1, Pattern 2 output value is -1
Pattern 1 Pattern 2

-1 -1 -1 -1 -1 -1
-1 +1 +1 +1 -1 +1
-1 -1 -1 +1 -1 +1
Chapter 2 Unsupervised Learning Network

Q.25 What is meant by unsupervised learning, Explain.

Q.26 Explain Mexican hat network/ Discuss Mexican hat network / Note on
Mexican hat network
Q.27 Explain Hamming network/ Discuss Hamming network / Note on
hamming network.
Q 28 Explain Kohonen self-organizing/ Discuss Kohonen self-organizing / Note
on Kohonen self-organizing
Q.29 Explain Learning vector quantization / Discuss Learning vector
quantization / Note on Learning vector quantization.
Q.30 Explain Counter propagative network/ Discuss Counter propagative
network / Note on Counter propagative network.
Q.31 Explain Adaptive resonance theory network/ Discuss Adaptive resonance
theory network / Note on Adaptive resonance theory network.
Q.32 What is meant by content addressable memory network, Explain.
Q.33 Mention the types of associate memory network, state the advantages of
associative memory network.
Q. 34 Explain auto-associative network/ Discuss auto-associative network/ Note
on auto-associative network.
Q. 35 Explain hetro-associative network/ Discuss hetro-associative network/
Note on hetro-associative network.
Q.36 Explain bi-directional associative network/ Discuss bi-directional
associative network/ Note on bi-directional associative network.
Q.37 Explain Hopfield network/ Discuss Hopfield network/ Note on Hopfield
network.
Q.38 Explain Temporal associative network/ Discuss Temporal associative
network/ Note on Temporal associative network.
Q. 39 Explain BAM’s network/ Discuss BAM’s network/ Note on BAM’s
network.
Q.40 Explain the terms Local minima and Global minima.
Q.41 A MaxNet has three inhibitory weights with € = 0.25. The net is initially
activated by the input signal [0.1, 0.3, 0.9]. The activation function f(x) = x if x
≥ 0 , 0 if x < 0. Find the winning neuron.
Q. 42 Construct MaxNet with five neurons having initial activation of five
nodes [0.5, 0.9, 1, 0.9, 0.9]. The activation function f(x) = x if x ≥ 0, 0 if x < 0.
Q.43 Construct the action of Maxnet with 4 neurons and inhibitory weight € =
0.3. The neurons given initial activation input signal a1(0) =0.3, a2(0) = 0.3,
a3(0) = 0.5, a4(0) = 0.7. Simulate the iteration until coverage.
Q. 44 Construct a Maxnet with four neurons and inhibitory weight € =0.2, given
the initial activations as follows a1(0) = 0.3; a2(0) = 0.5; a3(0) = 0.7; a4(0) = 0.9
The activation function f(x) = x if x > 0 , 0 if x ≤ 0.
Q. 45 Solve the Hamming network to cluster four vectors. Given the exemplar
vectors e(1) =[1 -1 -1 -1] and e(2) = [-1-1-1 1], for the bipolar input vectors
X1 = [-1 -1 1 -1] , X2 = [-1 -1 1 1] , X3 = [-1 -1 -1 1], X4 = [1 1 -1 -1]
Q. 46 Hamming net that has the following two exemplar vectors:
e (1) = [1 −1 −1 −1], e (2) = [ −1 −1 −1 1]. Following four vectors
x(1) = [1 1 −1 −1], x (2) = [1 −1 −1 −1], x (3) = [−1 −1 −1 1], x(4) = [−1 −1 1 1]
Q. 47 Solve the Hamming network to cluster four vectors. Given the exemplar
vectors e(1) =[1 -1 -1 -1] and e(2) = [-1-1-1 1], for the bipolar input vectors
X1 = [-1 -1 1 -1], X2 = [-1 -1 1 1], X3 = [-1 -1 -1 1], X4 = [1 1 -1 -1]
Q. 48 Hamming net that has the following two exemplar vectors:
e (1) = [1 −1 −1 −1], e (2) = [ −1 −1 −1 1]. Following four vectors
x(1) = [1 1 −1 −1], x (2) = [1 −1 −1 −1], x (3) = [−1 −1 −1 1], x(4) = [−1 −1 1 1]
Q. 49 Consider a Kohonen self-organizing net with two cluster units and five
input units. The weight vectors for the cluster units are given as
W1 = [1.0 0.9 0.7 0.5 0.3] W2 = [0.3 0.5 0.7 0.9 1.0]
Using the Euclidean distance find the winning cluster unit for input pattern
[0.0 0.5 1.0 0.5 0.0]. the learning rate is 0.25
Q. 50 Given a Kohonen self-organizing map with weights w1 = [0.7 0.3 0.1 0.6
1.0] and w2 = [ 0.5 0.2 0.4 0.9 0.5]. Find the cluster unit close to input vector
(0.35, 0.05), the learning rate is 0.25.
Q.51Construct a Kohonen self-organizing feature map to cluster the four given
vectors, [0 0 1 1], [1 0 0 0], [0 1 1 0] and [0 0 0 1]. The number of clusters to be
formed is two. Initial learning rate is 0.5.
Q. 52 Construct a Kohonen self-organizing feature map to cluster four vectors
[0 0 1 1], [1 0 0 1], [0 1 0 1], [1 1 1 1]. The maximum clusters to be formed is 2
and learning rate is 0.25. Use random initial weights.
Q. 53 Construct and test BAM network to associate letters E and F with simple
bipolar input-output vectors. The target output for E is (-1, 1) and for F is (1, 1).
The display matrix is 5 x 3.
### ###
#** ###
### #**
#** #**
### #**
‘E’ ‘F’
Q. 54 Construct and test BAM network to associate letters I and C with simple
bipolar input-output vectors. The target output for I is (1, -1) and for C is (-1, 1).
### ###
*#* ##*
### ###
‘I’ ‘C’
Chapter 3 Special Networks

Q. 54 State the importance of third-generation neural network.

Q. 55 Explain Simulated annealing network/ Discuss Simulated annealing
network/ Note on Simulated annealing network
Q. 56 Explain Boltzmann machine/ Discuss Boltzmann machine / Note on
Boltzmann machine.
Q. 57 Explain Gaussian machine/ Discuss Gaussian machine / Note on Gaussian
machine.
Q. 58 Explain Cauchy machine/ Discuss Cauchy machine / Note on Cauchy
machine.
Q. 59 Explain Cognitron network/ Discuss Cognitron network / Note on
Cognitron network.
Q. 60 Explain Optical neural network/ Discuss Optical neural network / Note on
Optical neural network.
Q. 61 Explain Spiking neural network/ Discuss Spiking neural network / Note
on Spiking neural network.
Q. 62 Explain Convolutional neural networks/ Discuss Convolutional neural
networks / Note on Convolutional neural networks.
Q. 63 Explain Deep learning neural networks/ Discuss Deep learning neural
networks/ Note on Deep learning neural networks.
Q. 64 Explain Extreme learning machine model/ Discuss Extreme learning
machine model / Note on Extreme learning machine model.
Q. 65 Explain Probabilistic neural network/ Discuss Probabilistic neural
network/ Note on Probabilistic neural network.
Chapter 4 Introduction to Fuzzy logic

Q. 66 Explain classical set and fuzzy set.

Q. 67 State the importance of fuzzy set.
Q. 68 Discuss the operations of classical set.
Q. 69 Mention the properties of classical set.
Q. 70 Explain the terms
(a) Degree of membership function (b) Power set
(c) Cardinality of set (d) Normal fuzzy set
(e) Subnormal fuzzy set (f) Convex fuzzy set
(g) Non-convex fuzzy set (h) Height of a fuzzy set
(i) Sub-normal fuzzy set (j) Crossover point in fuzzy
(k) Lambda-cut in fuzzy set
Q.71 Explain Fuzzification/ Discuss Fuzzification/ Note on Fuzzification.
Q.72 Define membership function and sate its importance in fuzzy logic.
Q.73 Mention the methods of assigning membership values to fuzzy set, explain
any three of the methods.
Q. 74 Explain defuzzification, state the necessity of defuzzification.
Q.75 Mention the defuzzification methods and explain any three.
Q. 76 Note on Fuzzy numbers.
Q. 77 Explain with suitable diagrams and examples
(a) Reflexivity (b) Symmetry (c) Transitive

Q. 78 Find the power set and cardinality of the given set X= {2, 4, 6}. Fine the
cardinality of power set.

Q. 79 Find the power set, cardinality and cardinality of power set

(a) X = {1, 3, 5, 7, 9} (b) Y = {2, 4, 6, 8, 10}

Q. 80 Consider two given fuzzy sets

1 0.3 0.5 0.2 0.5 0.4 0.1 1
𝐴 = {2 + 4 + 6 + 8 } 𝐵 = { 2 + 4 + 6 + 8}
Perform union intersection, difference and complement over fuzzy sets A and
B.

Q. 81 Given two fuzzy set

1 0.75 0.3 0.15 0 1 0.6 0.2 0.1 0
𝐵1 = {1.0 + 1.5 + 2.0 + 2.5 + 3.0} 𝐵2 = {1.0 + 1.5 + + 2.5 + 3.0}
2.0
Find the following
(a) B1 U B2 (b) B1 ∩ B2 (c) B1
(d) B2
(e) B1|B2 (f) B1 U B2 (g) B1 ∩B2
(h) B1∩ B2
(i) B1 U B1 (j) B2 ∩ B2 (k) B2 U B2
Q. 82 Consider two fuzzy set
1 0.65 0.5 0.35 0 0 0.35 0.5 0.65 1
𝐴 = {2.0 + 4.0 + 6.0 + 8.0 + 10.0} 𝐵 = {2.0 + + 6.0 + + 10.0}
4.0 8.0
Find the following
(a) A U B (b) A U B (c) A (d) B (e) A ∩ B (f) A U B

(g) A U B (h) A ∩ B (i) A U A (j) A ∩ A (k) B U B (l) B ∩ B

Q.83 The elements in two sets A and B are given as

A = {2, 4} and B = {a, b, c}, Find the various cartesian products of these two
sets.

Q. 84 Consider the following two fuzzy sets

0.3 0.7 1 0.4 0.9
𝐴 = { + + } 𝐵 = { + } Perform the cartesian
𝑥1 𝑥2 𝑥3 𝑦1 𝑦2
product over these given fuzzy sets.
Q. 85 The elements in two sets X and Y are given as X = {1, 2, 3} and Y = {p,
q, r}. find the various cartesian products of these two sets.

Q. 86 For the fuzzy sets given

0.5 0.2 0.9 1 0.5 1
𝐴 = {𝑥 + 𝑥 + 𝑥 } 𝐵 = {𝑦 + + } Find relation R by
1 2 3 1 𝑦2 𝑦3
performing cartesian product over the given fuzzy sets.

Q. 87 It is necessary to compare two sensors based upon their detection levels

and gain settings. The table of gain setting and sensor detection levels with a
standard item being monitored providing typing membership values to represent
the detection levels for each sensor is given in table 1,

Gain setting Detection level of sensor 1 Detection level of sensor 2

0 0 0
10 0.2 0.35
20 0.35 0.25
30 0.65 0.8
40 0.85 0.95
50 1 1
Table 1
The universe of discourse x = {0, 10, 20, 30, 40, 50} and the membership
functions for the two sensors in discrete form as,
0 0.2 0.35 0.65 0.85 1
𝐷1 = {0 + 10 + 20 + 30 + 40 + 50}

0 0.35 0.25 0.8 0.95 1

𝐷2 = { + + + + + } Find the following
0 10 20 30 40 50
(a) µ D1 U D2 (x) (b) µ D1 ∩ D2 (x) (c) µ D1 (x) (d) µ D2 (x) (e) µ D1 U D1 (x)

Q. 88 Implement Union, Intersection, Complement and difference on fuzzy set

0 0.1 0.3 0.5 0.57 0.6
(a) 𝐿 = { 100 + 200 + 300} 𝑀 = {100 + 200 + 300}
1 0.65 0.5 0.35 0
(b) 𝐴 = {2.0 + + + + }
4.0 6.0 8.0 10.0

0 0.35 0.5 0.65 1

𝐵 = {2.0 + + 6.0 + + 10.0}
4.0 8.0

0 0.5 0.35 0.75 0.95 1

(c) 𝐼1 = { 0 + + + + + }
20 40 60 80 100

0 0.45 0.55 0.65 0.9 1

𝐼2 = { 0 + 20
+ 40
+ 60
+ 80 + 100
}

Q. 89 Three fuzzy sets are given below

0.1 0.3 0.7 0.4 0.2 0.1 0.3 0.3 0.4 0.5 0.2
𝑃={2 + + + + } 𝑄 = { 0.1 + + + + 0.5 + }
4 6 8 10 0.2 0.3 0.4 0.6

0.1 0.7 0.3

𝑇 = { + + } Perform the following operations over the fuzzy sets
0 0.5 1

(a) R = P x Q (b) S = Q x T (c) M1 = R o S (d) M2 = R o S

Chapter 5 Genetic Algorithm

Q. 1 State the importance of Genetic algorithm.

Q. 2 Explain the terms,
(a) Cell (b) Chromosomes (c) Genetics (d) Reproduction (e) Natural
selection (f) Individuals (g) Genes (h) Fitness (d) Population
Q.3 Mention the optimization and search techniques, explain any two.
Q. 4 Note on search space.
Q.5 Compare and contrast genetic algorithm with traditional algorithm.
Q.6 Explain simple genetic algorithm.
Q.7 Discuss the steps in general genetic algorithm.
Q.8 Mention the operators in genetic algorithm, explain three of them.
Q.9 Explain crossover.
Q.10 Mention the advantages and limitations of genetic algorithm.
Q.11 List the applications of genetic algorithm.